Multilingual Language Model Evaluation

LLM debate is usually evaluated by final answers, yet transcripts reveal whether later turns develop new arguments or return to earlier claims in new wording. We study this process with \textit{prior-argument similarity}, which compares extracted argument units with earlier units in the same debate. In controlled eight-turn debates over 71 motions, six languages, and four model agents, Chinese is the only tested language with a consistently positive gap relative to English across three multilingual embedding models. The gap persists across agents, turn positions, regression adjustment, metric variants, extraction-length controls, a second-extractor subset, and cross-encoder tail rescoring. Manual calibration shows weak item-level alignment but a high-similarity tail enriched for substantive repetition. A diversity-aware prompt lowers \textit{prior-argument similarity} across languages, yet does not significantly narrow the Chinese--English gap. Multilingual debate evaluation should therefore measure argumentative development over time and report both average and gap terms.

Multilingual reasoning evaluation overwhelmingly relies on translating English benchmarks, a practice that introduces linguistic artifacts and fails to test culturally-grounded reasoning. We introduce ADAGE (Analogical Difficulty-by-design Assessment for Grounded Evaluation), a language-agnostic pipeline that combines native-speaker curation with LLM-assisted generation to construct challenging, translation-free benchmarks for abstract analogical reasoning. We validate ADAGE by constructing benchmarks for Arabic, Amharic, and Japanese. Evaluating 14 open-weight models, we find a consistent cultural reasoning gap: models that perform well on English proverb reasoning struggle substantially on all three native benchmarks, with accuracy dropping by 12--52 percentage points relative to English. We release the pipeline, all three benchmarks, and the full evaluation suite.

We present DS@GT's submission to FinMMEval 2026 Task 1, a multilingual financial exam question answering benchmark spanning English, Spanish, Greek, Chinese, and Hindi. Financial certification exams such as the CFA, EFPA, and CPA demand structured domain reasoning that standard NLP benchmarks do not capture, and this challenge compounds across languages where retrieval and representation infrastructure is underdeveloped. We build a retrieval-augmented pipeline on LangGraph that detects query language and retrieves semantically relevant exemplars from a 30,209-entry multilingual knowledge base using BGE-M3 embeddings and FAISS indexing. The system then scores answers via Retrieval-Augmented Direct Scoring (RADS), reading next-token log-probabilities over candidate option letters rather than generating free-form output. For low-resource languages, we fuse per-language and cross-lingual retrieval indices using weighted Reciprocal Rank Fusion. Model selection is language-routed: Qwen3-14B for Arabic, Chinese, and Hindi; Qwen2.5-14B for English; and Llama-3.1-8B for Greek, a routing derived from empirical ablations that reveal substantial language-asymmetric performance gaps. Notably, chain-of-thought prompting significantly degrades Greek accuracy (90.7% to 20.9%), and enabling Qwen3's default thinking mode collapses Arabic RADS performance to near-chance levels. Our results indicate that effective multilingual financial reasoning requires language-aware retrieval, model routing, and deliberate scoring strategy selection.

Quiz rooms, trivia nights, and quiz shows challenge human knowledge across a wide range of topics, from canonical facts to everyday culture. In this paper, we examine whether large language models (LLMs) can perform competitively in such settings, using quiz-style questions to test them on both common and niche topics. We introduce TriviaRoomQA, a multilingual benchmark designed to evaluate everyday, culturally grounded, and long-tail knowledge across 288 topics. The benchmark contains 3,300 parallel multiple-choice questions in six European languages and additional 5,340 French-only questions for a more fine-grained case study. We evaluate 30 open-weight LLMs from European, Asian, and North American providers, covering models from 7 to 70B parameters. We find that models are strong on knowledge-intensive topics such as history, geography, and mathematics, but substantially weaker on everyday popular-culture topics such as celebrities, music, movies, and news. Moreover, model performance varies across languages even for the same underlying questions, suggesting that access to factual knowledge is not always language-independent. In sum, our dataset and experiments demonstrate an important knowledge gap which is not captured by existing academic-based saturated benchmarks.

Culture is lived through conversation, yet existing Indonesian cultural commonsense benchmarks evaluate LLMs on short and isolated prompts, stripping away the dialogic context in which cultural nuances actually surface. We introduce CultureTalk-ID, the first dialogue-based benchmark for cultural commonsense in Indonesian and its local languages, comprising 4,496 culturally grounded dialogues across 11 languages and 13 culturally salient topics, curated through a multi-stage human pipeline with native speakers to ensure authenticity. CultureTalk-ID introduces three complementary tasks, namely dialogue-based multiple-choice cultural commonsense reasoning, culturally faithful machine translation, and language steering, which jointly probe whether LLMs can understand, transfer, and generate culturally grounded language.

Grievance is one of the warning signs analysts look for when assessing threats of violence. It is increasingly measured at scale from online text, most often with word-level lexicons like the Grievance Dictionary that score by matching weighted terms. Such matching is a fast and transparent proxy, but it cannot resolve whether a term is asserted, quoted, negated, or condemned. These lexicons are also often evaluated on pools enriched with the very examples they retrieve, so a high score partly reflects agreement with the lexicon's own selection rule. Examining a five-language, 2{,}000-item evaluation pool, we find its halves separated almost perfectly by the lexicon itself: every item labeled ``random'' is in fact lexicon-negative, so the lexicon's apparent macro-AUROC of 0.686 collapses to a 0.500 floor fixed by construction. We keep the dictionary's 22-construct ontology but replace term matching with context-reading models, evaluated on a non-circular benchmark that separates unconditional-random, lexicon-positive, and lexicon-negative strata across five languages. Reading the full post rather than the target sentence alone helps most where the lexicon is silent, raising average precision on lexicon-negative text from 0.14 to 0.20, with the largest gains on quoted, implicit, and cross-sentence grievance. Together, these results show that grievance is measured more faithfully by reading the surrounding context, and more honestly when tested on text the lexicon did not select. We release our code and benchmark at https://github.com/behavioral-ds/multilingual_grievance.

Value alignment of Large Language Models (LLMs) has been shown to be culturally biased toward Western norms. This results in the mishandling of local values in multilingual societies such as Sri Lanka that have their unique cultural dynamics. Existing benchmarks overlook Sri Lankan-contextualized values in its official language Sinhala, hindering culturally sensitive evaluation and fine-tuning. To bridge this gap, we propose LKValues, the first survey-grounded resource suite for Sri Lankan value alignment. From a trilingual survey of 205 respondents, blending adapted global frameworks and LLM-elicited local constructs, we derive 40 majority-endorsed societal values. Using these values, we construct LKvaluesIT, a Sinhala-English news-derived instruction corpus containing 150k scenario-based instances, and LKvaluesBench, a value-sensitive evaluation benchmark of 1,000 instances. We evaluate a set of proprietary and open-weight LLMs with LKvaluesBench. We fine-tune three open-weight base models (Qwen3.5-4B-Base, Qwen3.5-9B-Base, and Aya-Expanse-8B-Base). Our experiments show that newer and larger LLMs still exhibit low-resource and cultural value-alignment gaps. LKValues fine-tuning improves Qwen-family models in English and Sinhala, reducing invalid outputs and cross-lingual disparities, though gains remain model-family dependent. These highlight LKValues efficacy in embedding Sri Lankan values, offering a replicable pipeline for low-resource, country-specific pluralist value alignment. The dataset is publicly available at https://github.com/NextME14/LKValues.

Culturally loaded translation poses unique challenges for machine translation (MT), as meanings are deeply embedded in socio-cultural contexts beyond surface linguistic forms. Although large language models (LLMs) have enabled MT systems to achieve human-like quality in many scenarios, their ability to handle culturally loaded expressions remains underexplored. In this study, we systematically investigate the challenges posed by culturally loaded translation in LLM-based MT systems. We construct a Chinese-Japanese bilingual dataset from the culturally representative corpus Dream of the Red Chamber, containing 500 segments across diverse cultural categories. Using a comprehensive evaluation protocol, we reveal three main challenges: (1) task challenges, where frontier LLMs exhibit notable performance gaps and struggle with culturally loaded content; (2) human evaluation challenges, where evaluator backgrounds lead to substantial disagreement in translation judgments; and (3) automatic evaluation challenges, where widely used metrics fail to reliably assess translation quality for this task. These findings may offer valuable insights for culture-oriented translation research in both computational science and linguistics.

FinMMEval 2026 Task 2 evaluates short-answer financial question answering over multilingual evidence. Each final-test item pairs an English question with financial statements and news in English, Chinese, Japanese, Spanish, and Greek. Participating systems submit one concise answer per item in JSONL format. The final-test set contains 256 items, split evenly between easy and expert tiers; each tier contains four question templates instantiated over 32 company-report groups. Gold answers were withheld during submission, and systems were ranked by macro-averaged item-level ROUGE-1 F1 against organizer-held reference answers. The final leaderboard includes 12 ranked submissions. The strongest systems are closely clustered, with the top four separated by less than one percentage point in ROUGE-1 F1. The submitted system papers document retrieval-augmented generation, cross-lingual evidence handling, structured prompting, answer compression, and validation strategies.

FinMMEval 2026 Task 1 evaluates multilingual financial multiple-choice question answering in English, Chinese, Arabic, and Hindi. The task tests whether systems can select the correct answer to finance questions involving domain terminology, numerical interpretation, and conceptual financial reasoning across languages and scripts. The final-test set contains 800 questions, with 200 questions per language; gold answers were withheld during submission, and each language was ranked independently by accuracy. The final leaderboards contain 13 English, 11 Chinese, 11 Arabic, and 10 Hindi ranked submissions. Top accuracies range from 92.0% in Hindi to 97.5% in English and Arabic, with the same leading teams appearing near the top across all four languages. The documented systems used retrieval augmentation, direct answer-option scoring, language-specific prompting, selective self-consistency, confidence checks, and LLM-based review stages.

Although Large Language Models (LLMs) demonstrate remarkable multilingual fluency, their internal knowledge representations remain disproportionately biased toward high-resource languages. This leads to cross-lingual factual inconsistency, where they shift their empirical answer distributions based solely on the prompt language. We investigate whether these biases can be mitigated at inference time, forcing an English-prompted model to answer as if it were queried in target languages (German, Spanish, Bulgarian), and evaluate four intervention strategies: zero-shot contextual steering (persona prompting), internal representation manipulation via Contrastive Activation Addition (CAA), and lightweight weight modification via Direct Preference Optimization (DPO) trained on benchmark-derived factual data as well as conceptual generalization data. To assess alignment, we curate a multilingual factual dataset alongside a novel generalization benchmark comprising culturally rooted queries to determine whether factual interventions transfer to broader target-centric preferences. Experiments on Gemma 3 12B Instruct reveal persona prompting to be the strongest overall intervention, balancing efficacy, safety, and out-of-domain generalization. While CAA yields sharp inconsistency benchmark shifts, it is configuration-sensitive and risks knowledge degradation. DPO-based adapters offer permanent, yet narrower and less transferable gains. These findings suggest that cross-lingual inconsistency is at least partly a selection problem, and that simple contextual interventions may outperform more invasive methods for robust, transferable alignment.

Clinical NLP evaluation remains dominated by multiple-choice question answering (MCQA), which scores only final-answer accuracy and cannot detect when a model reaches the correct diagnosis while grounding it in irrelevant, absent, or contradictory evidence. We introduce MIRA-Ev, a clinical argument mining benchmark built on Spanish Médico Interno Residente (MIR) licensing-exam cases, re-annotated by expert clinicians with span-level premises, claims, and directed support/attack relations, and released in parallel Spanish (native), English, and Basque versions, the first clinical argumentation resource in Basque. MIRA-Ev organizes evaluation into a three-tier task hierarchy: evidence sentence retrieval, argumentative component extraction, and relation classification.

This paper reports on a collaboration between the Directorate-General for Translation (DGT) and the European Master's in Translation (EMT) to localise the MMLU dataset into 11 European languages. Beyond creating a more inclusive benchmark for LLM evaluation, the project offers master's students authentic, project-based professional training in translation, revision, project management, and multilingual coordination, while highlighting key methodological, administrative, and workflow challenges.

Automated analyses of privacy policies enable large-scale assessments of transparency in digital ecosystems, yet existing auditing pipelines remain predominantly English-centric. This limits their ability to systematically evaluate multilingual environments, as in the European Union, where many services disclose privacy practices only in local languages. This paper examines whether large language models (LLMs) can extend privacy policy analysis beyond English without requiring language-specific adaptation, thus empowering large-scale auditing in linguistically diverse app ecosystems. We assemble an evaluation corpus spanning all 24 official EU languages from translated versions of two established expert-annotated datasets (OPP-115 and MAPP) and assess translation fidelity through automated metrics and targeted legal-expert review. Our LLM-based classifier for identifying categories of personal data collection achieves stable cross-lingual performance, with macro-F1 scores ranging between 0.91 and 0.94. We then leverage this capability in a large-scale audit of 2,611 Android applications from the Spanish Google Play Store. Combining multilingual privacy policy analysis with the evaluation of corresponding privacy labels and runtime network traffic exposes an important linguistic barrier: public-sector apps predominantly provide privacy policies in Spanish, whereas popular commercial apps mostly provide them in English. We reveal systematic discrepancies between declared and observed practices, especially in public-sector apps. Overall, our results indicate how English-only privacy audits can systematically obfuscate transparency gaps in multilingual environments.

Safety evaluation of large language models is conducted predominantly in English and predominantly on frontier systems. Neither condition describes how such models are encountered in low-resource health settings, where small quantised systems are run locally and queried in local languages. We ask whether clinical safety established in English transfers to Hausa, and whether any failure is attributable to the language, the clinical task, or the class of model that low-resource deployment admits. Matched English-Hausa question pairs were built for three conditions of high burden in northern Nigeria: malaria, sickle cell disease, and tuberculosis, probing knowledge recall, emergency triage, a leading question inviting a contraindicated action, and a traditional-remedy claim. Six models were evaluated: five locally deployable systems of 4-9 billion parameters, two medically fine-tuned, and one frontier system. All 128 responses were scored against Nigerian national treatment guidelines by two fluent Hausa speakers working independently and blind to one another. Among locally deployable models, mean clinical correctness fell from 1.57 in English to -0.03 in Hausa, on a scale where 2 denotes a correct answer and -1 an actively harmful one. The frontier model moved from 2.00 to 1.75 and produced no response judged harmful in either language. Drift was consistent across all three conditions. Inter-rater agreement was substantial for clinical correctness (kappa = 0.70); agreement on harm was initially poor (kappa = 0.22) and is examined in detail. Because a frontier model answers the same questions competently in Hausa, the deficit is a property neither of the language nor of the clinical material, but of the deployable tier.

Evaluating large language models (LLMs) across languages remains challenging, as most multilingual benchmarks rely on translated English datasets, often obscuring linguistic and cultural specificity in the target language. This issue is particularly pronounced for less-resourced languages such as Kyrgyz, where reliable natively authored evaluation data are scarce. Building on previously introduced Kyrgyz-language evaluation datasets, this work reports the first systematic and large-scale evaluation of LLMs in Kyrgyz using the KyrgyzLLM-Bench benchmark suite. KyrgyzLLM-Bench comprises two natively authored datasets$-$KyrgyzMMLU and KyrgyzRC$-$together with carefully translated and manually post-edited versions of WinoGrande, HellaSwag, BoolQ, and TruthfulQA. We evaluate 26 open- and closed-source LLMs under zero-shot and few-shot settings, analyzing model performance, cross-lingual transfer, and the impact of translation artifacts on evaluation reliability. Across families and tasks, model rankings transfer broadly from English to Kyrgyz on WinoGrande and BoolQ, and to a lesser extent on MMLU, while HellaSwag exhibits a substantial English-Kyrgyz performance gap consistent with translation-induced plausibility shifts. Few-shot prompting improves several open-source models on reading comprehension but behaves inconsistently for proprietary models on translated tasks. We publicly release all datasets, evaluation code, and per-model results, and integrate the Kyrgyz tasks into a widely used multilingual evaluation framework to support future research on Kyrgyz NLP.

As Large Language Models (LLMs) grow more capable across diverse tasks, their (in)ability to generalize remains difficult to quantify and poorly understood beyond limited domains. In particular, LLMs are known to struggle generalizing multilingually, to languages outside of English, and that are poorly attested in their training data. To understand why this may be, and what enables some models to perform better than others, we turn to a long history of work across the cognitive sciences, arguing that successful generalization derives from appropriate representations in similarity space. We look at how well LLMs' representations capture the hierarchical similarity structure between distinct languages. Strikingly, we show LLMs' latent representations largely recover the hierarchical structure of the Indo-European language family tree -- grouping languages that are members of the same subfamily closely together in representation space. Furthermore, we show that the degree to which models reflect the similarity structure of languages correlates with their performance on XNLI, a multilingual natural language inference benchmark. This extends classic work on similarity-driven generalization at scale, showing how models that represent similar languages similarly generalize better from one language to another.

We present JOR-Bench, a collection of five Japanese-language benchmarks for evaluating the ability of large language models (LLMs) to formulate and solve operations research (OR) problems. Each benchmark is a Japanese translation of an existing English benchmark: IndustryOR, MAMO Complex LP, NL4OPT, OptiBench, and OptMATH, covering 1,319 problems spanning linear programming, mixed-integer programming, non-linear programming, and combinatorial optimization. JOR-Bench is a solver-independent benchmark that can be used with any solver or programming language, and consists of pairs of Japanese problem statements and expected numerical answers. We evaluate seven LLMs, including multilingual general-purpose models and Japanese-specialized models, on both the original English and the new Japanese versions, and compare performance across languages. For the main evaluation, we standardize execution with the Python interface to OR-Tools to make model outputs comparable and reproducible with open-source software. Our results show that OR formulation ability is largely language-neutral for strong multilingual models; the overall average accuracy difference between English and Japanese is only $-0.3$ pp. Yet error analysis reveals subtle cross-lingual differences, including a pragmatic disambiguation failure in some domains that causes models to output decision-variable values instead of the objective value when the prompt is in Japanese.

Moderation systems increasingly rely on external toxicity tools, but those tools are unreliable under code-mixing, transliteration, slang, and language mismatch. We study the \emph{conditional reliability} of toxicity priors in Indian multilingual and code-mixed short text: English toxicity, Indic abuse, and rule-based severity cues can be useful evidence, but only in some linguistic and abuse-severity contexts. We propose ToxGate, a trust-fusion head that conditions each auxiliary signal on the encoder representation before adding it to the prediction state. Across three short-text abuse datasets, four transformer encoders, and five seeds per setting, ToxGate improves over matched plain encoders in 10 of 12 in-domain settings and 7 of 8 transfer settings. The largest and most interpretable gains occur in high-risk moderation slices, including explicit slurs, violent threats, and cross-dataset transfer. The broader lesson is that moderation systems should treat external toxicity tools and priors as conditional evidence rather than fixed features or ground truth, in focused ablations, source-specific gating gives the strongest results in transfer, severe-abuse slices, and high-risk triage.

Large Language Models (LLMs) perform differently on identical programming tasks when prompted in different natural languages, a phenomenon known as language bias. While this behavior has been widely studied for general text generation, its impact on code generation quality and programming conventions remains largely unexplored. We investigate how the language used to describe programming tasks affects the source code generated by GPT-4o mini, DeepSeek, and Claude. Our study comprises 460 coding tasks spanning Python (230) and Java (230). We translate and manually curate the original English prompts into Chinese, Hindi, Spanish, and Italian while preserving their technical meaning. We evaluate the generated code using multiple dimensions, including functional correctness through test pass rates, structural quality using established code metrics, issues detected by static analysis tools, and lexical characteristics such as the language used in identifiers and comments. Our results show that (i) English prompts do not consistently produce the best functional correctness or code quality, (ii) the impact of prompt language depends on both the programming language and the LLM, and (iii) generated code frequently mixes English with the prompt language in comments and string literals. These findings provide the first curated multilingual benchmark for studying language bias in code generation and offer insights for developing more robust multilingual code generation systems.

LLM evaluators (trained reward models and prompted LLM-as-a-Judge) are routinely validated via pairwise accuracy. In a multilingual setting, this operates under the premise that high pairwise accuracy implies reliable, language-neutral scoring. We show that this assumption does not hold. We conduct experiments with semantically identical instruction-response pairs across 23 languages, and find that multilingual evaluators assign significantly different scores to different evaluation languages. The bias is statistically significant and consistent across eight open-weight evaluators of different architectures and training paradigms, persists in frontier judges, and is strongly correlated with language resource level: lower-resource languages are scored more generously. Meanwhile, these biases are invisible to pairwise accuracy: evaluators achieve above 90% pairwise accuracy, yet have up to 43% difference in acceptance rate across languages under a global decision threshold, meaning, for instance, that harmful content in lower-resource languages is more likely to pass safety filters. Per-language thresholds would require language identification, which can be defeated by code-switched prompts. We then investigate why lower-resource languages receive higher rather than lower scores, and we find that model uncertainty is linked with the effect: models tend to give higher scores when less confident, both under negative log-likelihood and under token-free uncertainty measures; however, language identity remains a significant predictor after controlling for uncertainty, and the bias cannot be explained away by content difficulty alone, but is a structural, language-level misalignment.

While Large Language Models (LLMs) excel in many general NLP tasks, their formal reasoning capabilities are often compromised by content effects, demonstrating a measurable bias towards real-world plausibility. In this paper, we present our system for SemEval-2026 Task 11, which evaluates the ability of models to disentangle formal logic from content across 12 languages with and without distractor premises. We address this challenge using mDeBERTa-v3 networks fine-tuned on a synthetic, rule-based dataset of syllogistic schemes to avoid the semantic noise of LLM-augmented data. To explicitly decouple plausibility from logical structure, our training pipeline employs a multi-objective loss function combining Adaptive Group Distributionally Robust Optimization (DRO), a scheduled differentiable bias penalty, and KL-Divergence consistency regularization. Our system achieved #1 ranks and perfect Ranking Scores (100.0) with 0.00% bias and 100.0% accuracy on Subtask 1 (English), Subtask 2 (Noisy English), and Subtask 3 (Multilingual). On the highly complex Subtask 4 (Noisy Multilingual), the system achieved the 6th rank with 89.06% Accuracy and F1-score, alongside a limited 2.89% Bias and a 37.78 Ranking Score. Our dataset generation engine and codebase are publicly available to facilitate future work on robust logical reasoning.

Critical thinking is a fundamental skill that helps learners move beyond simple memorization. One way to develop this skill is through high-order questioning. However, crafting such questions remains a challenge for educators, and classroom practices tend to rely on low-order questions. Large Language Models have demonstrated strong capabilities in generating high-order questions, especially when guided by prompts based on Bloom's Taxonomy. Yet, existing research has largely centered on this framework and focused only on English. This study addresses these gaps by introducing prompts grounded in two alternative frameworks: Claim-Evidence-Reasoning and Divergent Questioning within a multilingual context using Basque, Spanish, and English. Results indicate that while both an open-source and a proprietary model rather effectively generate questions in all three languages, only about half of the answerable questions are recognized by teachers as high-order. A positive finding is that the alternative frameworks produce structurally and conceptually varied questions, suggesting they could complement each other and provide viable alternatives to Bloom's Taxonomy.

Studies of bias in LLM-as-judge systems typically build synthetic corpora by prompting an LLM to generate a hallucinated answer to pair with a factual one, then presenting both to a judge. We report a case in which this generation step silently failed, and use it to argue that the failure mode is structural rather than incidental. In a multilingual (Turkish/English) faithfulness-judgment corpus, a decoding-budget parameter shared between judging and generation calls truncated one producer's hallucinated answers to a few words. The resulting items produced a large, statistically robust effect: a 32-point cross-lingual collapse in one judge's selection accuracy, replicated from N=50 to N=500, explained by a three-layer mechanistic account, and confirmed by a controlled producer-swap experiment, none of which was real. The effect vanished to ceiling once the shared parameter was corrected, and only manual reading of the raw generations, not any aggregate statistical check, exposed the fault. A second measured bias (Markdown-formatting preference) was not fabricated but distorted by the same fault, its magnitude and in one case its sign shifting with stimulus length, a mode aggregate metrics cannot distinguish from the first. We frame the underlying vulnerability using the test oracle problem: corpora whose negative examples are LLM-generated carry no mechanical way to verify item integrity, while corpora built by deterministic perturbation of a gold answer carry an item-level oracle for free. A positive control supports this claim directly: an analogous fault injected into a minimal perturbation-based corpus is caught with 100% accuracy by a zero-cost, zero-human gold-to-negative string comparison. We close with a validation protocol, derived from our own case, for analysts working in the oracle-less regime that we argue describes most contemporary multilingual LLM-as-judge corpora.

Can a language model estimate its familiarity with an entity before generating an answer? We study activations at the final prompt token in twelve instruction-tuned models from the Bielik, PLLuM, Gemma-4, and Qwen3 families, using a new dataset of 1,440 Polish entities spanning four domains and ten Wikipedia-pageview deciles, plus fabricated controls. Familiarity-probe scores separate real from fabricated entities in every family; in the Polish-adapted Bielik and PLLuM families they additionally track entity popularity (model-mean Spearman $ρ$ 0.28-0.57, versus at most 0.11 in Gemma-4 and Qwen3), a pattern more strongly associated with Polish adaptation than with parameter count in this model sample. In a paired experiment on two families, probes retain 96-101% of within-language AUROC when the Polish question stem is replaced with an English one around unchanged entity names, showing robustness to prompt language in this setting. In Gemma-4-12B, the only model that natively refuses, adding a one-dimensional familiarity direction at a single layer moves refusal rates monotonically in both directions (0.24 to 1.00 on well-known entities; 0.73 to 0.00 on unknown ones). Finally, a calibrated familiarity probe is competitive among pre-generation abstention gates, although post-generation detectors better predict behavioral error on average. These results support a graded pre-generation entity-familiarity readout, and a separation between representational familiarity and the policy that converts it into abstention.

Teams measuring whether large language models (LLMs) recommend a brand face a reproducibility problem: ask the same question twice and the answer moves. Practice resamples each prompt a few times (commonly five) and averages, treating within-prompt resampling as the source of the noise. But a measured brand score moves for at least four separable reasons: within-prompt resampling, prompt paraphrase, model identity, and query language. We specify a crossed random-effects (generalizability-theory) decomposition that partitions the total variance of a response-level brand outcome into these four sources, and embed the components in a decision-study allocation that returns how many repeats, paraphrases, models, and languages to buy for a target reliability. We apply it to a fully crossed corpus of 12,933 LLM responses on 20 Central and Eastern European brands, 8 languages, and 3 models (GPT-5.2 and Gemini 3 Flash in parametric mode, Perplexity in grounded retrieval), with a stability subset of 1,435 cells resampled about five times. The outcome is per-response multilingual sentiment polarity. Query language is the largest systematic facet (26.5% of the variance of one response) against 1.5% for brand identity (ICC 0.0146), so a single AI answer carries almost no brand-discriminating signal. Once a cell term isolates pure resampling, resampling is 34.8% of variance and the brand-in-context interaction 29.6%; brand-by-language is 8.6% (a bilingual penalty) while brand-by-model and brand-by-prompt are near zero. Per unit of query budget, adding languages and models reduces relative-error variance far more than adding repeats: a repeat past the fifth reduces it by only 0.0003. Brand-ranking reliability stays low, near 0.01 for a single answer and about 0.36 at the full crossed design, so reliability is bought by spreading across languages and models, not by repeating one prompt.

The evaluation of mathematical reasoning in large language models (LLMs) has predominantly focused on high-resource languages like English. This has created a significant barrier to the equitable development and deployment of AI in linguistically diverse regions such as Bangladesh, where over 230 million people speak Bengali. Despite this global significance, there has been minimal prior work on mathematical reasoning in Bengali and no existing research that systematically benchmarks a perturbated Bengali mathematical dataset, leaving a critical void in assessing model robustness and true comprehension beyond pattern recognition. This study addresses this gap by introducing GSM-Plus-BN, a novel perturbated Bengali mathematical dataset derived from the English GSM-Plus benchmark and verified by human translators. We evaluate six open-source LLMs Qwen3-32B, Llama-3.1-8B-Instant, Llama-3.3-70B-Versatile, Llama-4-Scout-17B-16E-Instruct, GPT-OSS-120B, and GPT-OSS-20B using a benchmark of 9,000 evaluation samples comprising 1,000 seed questions and 8,000 perturbed variants under both Standard Prompting and Chain-of-Thought (CoT) Prompting. Experimental results show that GPT-OSS-20B achieves the highest seed question accuracy of 96.08% under Standard Prompting, while larger models such as Llama-3.3-70B and GPT-OSS-120B demonstrate superior robustness across perturbation types. Furthermore, CoT prompting substantially improves reasoning for most models compared to Standard Prompting, yet a notable performance gap persists across all models relative to their English benchmarks, underscoring the inherent difficulty of perturbed Bengali text. This research makes a foundational contribution by providing GSM-PLUS-BN as a new resource and baseline for future Bengali mathematical reasoning research.

Institutions collect far more open-ended teaching-evaluation feedback than they read. A prior study introduced a validated protocol for classifying such comments by thematic category and sentiment, built from a documented annotation guide, an intra-annotator reliability measurement, stratified cross-validation, and a held-out evaluation on a Spanish institutional corpus with a frozen-encoder design. Two questions limit its reuse: whether a protocol fixed to 2019-era frozen embeddings stays competitive as representation methods advance, and whether it transfers to a second language. We re-run it on the original Spanish data across three representation generations, sparse lexical features, frozen transformer embeddings, and prompted large language models, and transfer its sentiment task to English with a balanced 45,000-comment corpus checked against an aspect-labeled education dataset. Treating paired comparisons as descriptive, we find the protocol durable: a 2026 frontier model posts the highest thematic F1 on the hardest Spanish task, yet shows no sentiment advantage over a cheap model and no descriptive separation from it on English, so model choice is a deployment decision, not a property of the method.

Language models are increasingly used for moral decision-making across diverse linguistic and cultural contexts, yet existing work overlooks multilinguality on three aspects: 1) multilingual evaluation benchmarks use direct translation, failing to adapt culture-specific items; 2) inference-time methods for moral reasoning rely on static, English-centric scaffolds and lack grounding in moral theory; 3) training methods for moral decision-making typically require expensive supervision from stronger models or human annotators. We address these gaps with three contributions. First, we introduce MCLASH, a multilingual moral decision-making benchmark to capture culturally situated moral intuitions and social norms across languages. Second, we propose MET (Multilingual Ethics with Theory-grounded reasoning), a two-step prompting method built on expert-curated, theory-based grounds drawn from psychology and philosophy: the model first selects situation- and culture-specific grounds, then reasons over them in the native language of the user. Third, we introduce MET-D (MET-Distillation), which enhances the second step through a self-distillation training stage that requires no external supervision. MET-D improves macro-F1 over the base model on all three models of different sizes and families (Qwen3-4B, Qwen3-8B, Gemma3-4B), by an average of 3.71 points on MCLASH and 4.23 on MMoralExceptQA, with a peak MCLASH gain of 12.94 points for Malay on Qwen3-8B. We further reveal that MET-D increases native-language reasoning by 62.13 points on average, and that beneficial grounds differ systematically across cultures. Together, these contributions open the path for culture-aligned, theory-grounded multilingual moral reasoning.

Reasoning Language Models (RLMs) achieve their strongest performance when they reason in English, the language for which reasoning-oriented training data is most abundant. However, reasoning trace is a clue for model interpretability and safety, and useful in practice for both the model users and for model developers. Thus, it is desirable to be able to develop a model that reasons in a language of the user's choice, while still maintaining strong reasoning performance. To this end, we study the feasibility of training a model that reasons in Japanese. We develop a Japanese-reasoning variant of Qwen-3-Swallow-8B, which is a Japanese LLM continually pretrained from Qwen-3-8B, with GRPO and evaluate it across coding, math, and science benchmarks. The study shows that reasoning-language control is feasible by training a Japanese continually pretrained model with GRPO. However, its performance is at best on par with strong English-reasoning baselines on several benchmarks. We also evaluate the trained model on Japanese cultural benchmarks and observe that the model's performance is worse than the baseline models, suggesting that the reasoning in Japanese does not immediately improve performance on culturally relevant tasks for free.